Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    say "%"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astics
    -0.07
    ZN
    -0.07
     addressed
    -0.07
    .shopping
    -0.07
    uting
    -0.07
    _languages
    -0.07
     player
    -0.07
    �
    -0.07
    �
    -0.07
    윽
    -0.07
    POSITIVE LOGITS
     unchanged
    0.08
    今晚
    0.07
    无需
    0.07
    评审
    0.07
     statewide
    0.07
     снова
    0.07
    ≋
    0.07
     controversial
    0.07
     Nhà
    0.07
    	tmp
    0.07
    Act Density 0.043%

    No Known Activations